The github repo includes (among other things) a script (relying on python-pptx) to output decomposed layer images into a pptx file “where you can edit and move these layers flexibly.” (I've never user Powerpoint for this, but maybe it is good enough for this and ubiquitous enough that this is sensible?)
I saw some people at a company called Pruna AI got it down to 8 seconds with Cloudflare/Replicate, but I don't know if it was on consumer hardware or an A100/H100/H200, and I don't know if the inference optimization is open-source yet.
with torch.inference_mode():
output = pipeline(**inputs)
output_image = output.images[0]
for i, image in enumerate(output_image):
image.save(f"{i}.png")
Unless it's a joke that went over my head or you're talking about some other GitHub readme (there's only one GitHub link in TFA), posting an outright lie like this is not cool.
The word "powerpoint" is not there, however this text is:
“The following scripts will start a Gradio-based web interface where you can decompose an image and export the layers into a pptx file, where you can edit and move these layers flexibly.”
Oh okay I missed it, sorry. But that’s just using a separate python-pptx package to export the generated list of images to a .pptx file, not something inherent to the model.
